Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MACRec: a Multi-Agent Collaboration Framework for Recommendation

Zhefan Wang, Yuanqing Yu, Wendi Zheng, Weizhi Ma, Min Zhang

TL;DR

This work introduces MACRec, a novel framework designed to enhance recommendation systems through multi-agent collaboration, unlike existing work on using agents for user/item simulation, which aims to deploy multi-agents to tackle recommendation tasks directly.

Abstract

LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks. Recognizing the current gap in leveraging agent capabilities for multi-agent collaboration in recommendation systems, we introduce MACRec, a novel framework designed to enhance recommendation systems through multi-agent collaboration. Unlike existing work on using agents for user/item simulation, we aim to deploy multi-agents to tackle recommendation tasks directly. In our framework, recommendation tasks are addressed through the collaborative efforts of various specialized agents, including Manager, User/Item Analyst, Reflector, Searcher, and Task Interpreter, with different working flows. Furthermore, we provide application examples of how developers can easily use MACRec on various recommendation tasks, including rating prediction, sequential recommendation, conversational recommendation, and explanation generation of recommendation results. The framework and demonstration video are publicly available at https://github.com/wzf2000/MACRec.

MACRec: a Multi-Agent Collaboration Framework for Recommendation

TL;DR

This work introduces MACRec, a novel framework designed to enhance recommendation systems through multi-agent collaboration, unlike existing work on using agents for user/item simulation, which aims to deploy multi-agents to tackle recommendation tasks directly.

Abstract

LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks. Recognizing the current gap in leveraging agent capabilities for multi-agent collaboration in recommendation systems, we introduce MACRec, a novel framework designed to enhance recommendation systems through multi-agent collaboration. Unlike existing work on using agents for user/item simulation, we aim to deploy multi-agents to tackle recommendation tasks directly. In our framework, recommendation tasks are addressed through the collaborative efforts of various specialized agents, including Manager, User/Item Analyst, Reflector, Searcher, and Task Interpreter, with different working flows. Furthermore, we provide application examples of how developers can easily use MACRec on various recommendation tasks, including rating prediction, sequential recommendation, conversational recommendation, and explanation generation of recommendation results. The framework and demonstration video are publicly available at https://github.com/wzf2000/MACRec.
Paper Structure (19 sections, 2 figures, 2 tables)

This paper contains 19 sections, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Agents-based Recommendation
  4. Multi-agent Collaboration
  5. The MACRec Framework
  6. Framework Overview
  7. Agent Roles
  8. Manager
  9. Reflector
  10. User/Item Analyst
  11. Searcher
  12. Task Interpreter
  13. Applications on Recommendation Scenarios
  14. Rating Prediction (RP)
  15. Sequential Recommendation (SR)
  16. ...and 4 more sections

Figures (2)

  • Figure 1: The Framework of MACRec. We take a sequential recommendation task as an example to show how these agents work collaboratively.
  • Figure 2: The web interfaces of our MACRec, along with a case of how three agents collaboratively address a conversational recommendation task. The interface is composed by the leftmost configuration panel and the main interaction panel.